Nomic Embed Text

Open-source text embedding model that outperforms OpenAI models on key benchmarks

Model Details

A large context length text encoder that surpasses OpenAI text-embedding-ada-002 and text-embedding-3-small performance on short and long context tasks. Specialized for generating text embeddings, semantic search, and RAG applications.

Parameters

137 million

Context Window

8192 tokens

Recommended Use

Ideal for retrieval-augmented generation (RAG), semantic search, clustering, and document similarity tasks.

Supported Languages

Multilingual

Usage Examples

Installation:

pip install tinfoil

Inference:

from tinfoil import TinfoilAI

client = TinfoilAI(
    enclave="nomic-embed-text.model.tinfoil.sh",
    repo="tinfoilsh/confidential-nomic-embed-text",
    api_key="YOUR_API_KEY",
)

embedding = client.embeddings.create(
    model="nomic-embed-text",
    input="The quick brown fox jumps over the lazy dog.",
)
print(embedding.data[0].embedding)